INDEX

Explanations

instances of the word "example" used to illustrate or clarify points

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 noires

-0.70

 blanches

-0.59

 normaux

-0.55

']}

-0.55

']/

-0.53

leau

-0.52

 {}'.

-0.50

 eigentlichen

-0.50

{}'.

-0.50

 debout

-0.50

POSITIVE LOGITS

 Например

1.04



1.00

 exemple

0.98

Например

0.98

 example

0.95

ViewFeatures

0.94

 eksempel

0.94

ául

0.93

AddTagHelper

0.92

 ejemplo

0.92

Activations Density 0.097%

instances of the word "example" used to illustrate or clarify points

No Comments

No Known Activations